© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52561
    Prev
    Next
    INDEX
    Explanations

    vase, jug, mug, ceramic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vido
    -0.10
    ìĤ¬íķŃ
    -0.10
     ribbon
    -0.09
    æĪijåıĪ
    -0.08
    æĬľ
    -0.08
    éģįåıĬ
    -0.08
    å·
    -0.08
    å§Ĺ
    -0.08
    æ·±åĬłå·¥
    -0.08
    agne
    -0.08
    POSITIVE LOGITS
    ICAL
    0.10
    çĽĤ
    0.10
    çłµ
    0.10
    çł´è£Ĥ
    0.09
    çļ¿
    0.09
    cer
    0.08
    èĭ£
    0.08
    æ¼ıæ°´
    0.08
    /fixtures
    0.08
    Filled
    0.08
    Activations Density 0.029%

    No Known Activations